The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from external search results.
Ingestion points: Search result fields such as title, content, and infobox content are parsed from the SearXNG JSON response in scripts/search.py and printed to the agent's context.
Boundary markers: The script uses Markdown headers and styling (e.g., ## [title](url)) to format results, but does not implement explicit boundary delimiters or 'ignore embedded instructions' warnings to prevent the agent from following instructions found within search snippets.
Capability inventory: The skill uses urllib.request for network communication and is executed via the Bash tool.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from search results before it is presented to the agent.

searxng-search